An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width
Bayesian Neural Networks

v1v2 (latest)

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

16 November 2022

Finale Doshi-Velez

ArXiv (abs)PDF HTML

Papers citing "An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks"

19 / 19 papers shown

Title
Bayesian Model Selection, the Marginal Likelihood, and Generalization Sanae Lotfi Pavel Izmailov Gregory W. Benton Micah Goldblum A. Wilson UQCV BDL 110 58 0 23 Feb 2022
Wide Mean-Field Bayesian Neural Networks Ignore the Data Beau Coker W. Bruinsma David R. Burt Weiwei Pan Finale Doshi-Velez UQCV BDL 75 24 0 23 Feb 2022
Precise characterization of the prior predictive distribution of deep ReLU networks Lorenzo Noci Gregor Bachmann Kevin Roth Sebastian Nowozin Thomas Hofmann BDL UQCV 62 31 0 11 Jun 2021
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Geoff Pleiss John P. Cunningham 50 27 0 11 Jun 2021
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed Maria Refinetti Sebastian Goldt Florent Krzakala Lenka Zdeborová 63 74 0 23 Feb 2021
Neural Network Gaussian Process Considering Input Uncertainty for Composite Structures Assembly Cheolhei Lee Jianguo Wu Wei Cao Xiaowei Yue 36 19 0 21 Nov 2020
Deep Equals Shallow for ReLU Networks in Kernel Regimes A. Bietti Francis R. Bach 69 90 0 30 Sep 2020
Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS Lin Chen Sheng Xu 129 94 0 22 Sep 2020
When Do Neural Networks Outperform Kernel Methods? Behrooz Ghorbani Song Mei Theodor Misiakiewicz Andrea Montanari 86 188 0 24 Jun 2020
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro Du Phan Neeraj Pradhan M. Jankowiak 58 358 0 24 Dec 2019
Towards Understanding the Spectral Bias of Deep Learning Yuan Cao Zhiying Fang Yue Wu Ding-Xuan Zhou Quanquan Gu 98 219 0 03 Dec 2019
Why bigger is not always better: on finite and infinite neural networks Laurence Aitchison 218 54 0 17 Oct 2019
A Fine-Grained Spectral Perspective on Neural Networks Greg Yang Hadi Salman 76 113 0 24 Jul 2019
On the Spectral Bias of Neural Networks Nasim Rahaman A. Baratin Devansh Arpit Felix Dräxler Min Lin Fred Hamprecht Yoshua Bengio Aaron Courville 152 1,451 0 22 Jun 2018
Gaussian Process Behaviour in Wide Deep Neural Networks A. G. Matthews Mark Rowland Jiri Hron Richard Turner Zoubin Ghahramani BDL 144 559 0 30 Apr 2018
Deep Neural Networks as Gaussian Processes Jaehoon Lee Yasaman Bahri Roman Novak S. Schoenholz Jeffrey Pennington Jascha Narain Sohl-Dickstein UQCV BDL 128 1,093 0 01 Nov 2017
Student-t Processes as Alternatives to Gaussian Processes Amar Shah A. Wilson Zoubin Ghahramani GP 90 203 0 18 Feb 2014
Analysis and Extension of Arc-Cosine Kernels for Large Margin Classification Youngmin Cho Lawrence K. Saul 94 28 0 16 Dec 2011
The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo Matthew D. Hoffman Andrew Gelman 165 4,304 0 18 Nov 2011

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.